© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 32566
    Prev
    Next
    INDEX
    Explanations

    code structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     strangely
    -0.13
     surprisingly
    -0.11
     ‘
    -0.11
     accidentally
    -0.10
     whilst
    -0.10
     unintention
    -0.10
     ignor
    -0.10
    ...",
    -0.10
     reluct
    -0.10
     invol
    -0.10
    POSITIVE LOGITS
     withd
    0.11
     nto
    0.10
     solo
    0.10
     Ensemble
    0.10
     Duo
    0.10
     Vog
    0.09
     Belarus
    0.09
     plenty
    0.09
     Pause
    0.09
     spotlight
    0.09
    Activations Density 0.003%

    No Known Activations